- Published
- 2021-05-18
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 8, pp. 6679-6687
- Cited by
- 227
- Open access
- Yes, diamond
- DOI
- 10.1609/aaai.v35i8.16826
Abstract
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient features. We demonstrate that TabNet outperforms other variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into its global behavior. Finally, we demonstrate self-supervised learning for tabular data, significantly improving performance when unlabeled data is abundant.
Cite this paper
Formatted from the source metadata, not typed by hand. For a whole reference list, use the citation generator or ask your assistant through Find Research.
- APA 7
Arık, S. Ö., & Pfister, T. (2021). TabNet: Attentive Interpretable Tabular Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 6679–6687. https://doi.org/10.1609/aaai.v35i8.16826
- MLA 9
Arık, Sercan Ö., and Tomas Pfister. "TabNet: Attentive Interpretable Tabular Learning." Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 8, 2021, pp. 6679–6687, https://doi.org/10.1609/aaai.v35i8.16826.
- Chicago
Arık, Sercan Ö., and Tomas Pfister. "TabNet: Attentive Interpretable Tabular Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (2021): 6679–6687. https://doi.org/10.1609/aaai.v35i8.16826.
- GOST
Arık S. Ö., Pfister T. TabNet: Attentive Interpretable Tabular Learning // Proceedings of the AAAI Conference on Artificial Intelligence. — 2021. — Vol. 35, № 8. — P. 6679–6687. — URL: https://doi.org/10.1609/aaai.v35i8.16826
- BibTeX
@article{ark2021tabnet, title = {{TabNet: Attentive Interpretable Tabular Learning}}, author = {Sercan Ö. Arık and Tomas Pfister}, journal = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2021}, volume = {35}, number = {8}, pages = {6679--6687}, doi = {10.1609/aaai.v35i8.16826}, url = {https://doi.org/10.1609/aaai.v35i8.16826} }- RIS
TY - JOUR AU - Arık, Sercan Ö. AU - Pfister, Tomas TI - TabNet: Attentive Interpretable Tabular Learning JO - Proceedings of the AAAI Conference on Artificial Intelligence VL - 35 IS - 8 SP - 6679 EP - 6687 PY - 2021 DA - 2021/05/18 DO - 10.1609/aaai.v35i8.16826 UR - https://doi.org/10.1609/aaai.v35i8.16826 ER -